ssh_mkdir

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries burden. Explains recursive creation, tolerance of existing parent dirs, and error on existing leaf. Lacks authentication details but implies SFTP use.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences with front-loaded action. Every sentence earns its place with specific behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and full parameter coverage, description explains recursive behavior and error handling effectively. Could mention permission assumptions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Adds value beyond schema: explains recursive like mkdir -p, notes absolute path requirement, and highlights password security. Schema already covers 100% of parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states action and method: 'Create a directory on a remote host via SFTP.' Distinguishes from sibling tools like ssh_delete, ssh_ls, etc.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides guidance on recursive flag behavior and error conditions. Could explicitly recommend against using ssh_exec for mkdir, but for a dedicated tool, context is adequate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.